© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 112458
    Prev
    Next
    INDEX
    Explanations

    results

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     midnight
    -0.08
     sacrifice
    -0.08
     capables
    -0.07
     army
    -0.07
     infancy
    -0.07
    �
    -0.07
     cann
    -0.07
    .expand
    -0.07
    चर
    -0.07
     महत्व
    -0.07
    POSITIVE LOGITS
    returned
    0.12
     результата
    0.11
     returned
    0.11
     responses
    0.11
    Returned
    0.11
    回来
    0.10
    结果
    0.10
    (Return
    0.10
    输出
    0.10
    結果
    0.10
    Activations Density 0.024%

    No Known Activations